# frozen_string_literal: true # WARNING ABOUT GENERATED CODE # # This file is generated. See the contributing guide for more information: # https://github.com/aws/aws-sdk-ruby/blob/master/CONTRIBUTING.md # # WARNING ABOUT GENERATED CODE require 'seahorse/client/plugins/content_length.rb' require 'aws-sdk-core/plugins/credentials_configuration.rb' require 'aws-sdk-core/plugins/logging.rb' require 'aws-sdk-core/plugins/param_converter.rb' require 'aws-sdk-core/plugins/param_validator.rb' require 'aws-sdk-core/plugins/user_agent.rb' require 'aws-sdk-core/plugins/helpful_socket_errors.rb' require 'aws-sdk-core/plugins/retry_errors.rb' require 'aws-sdk-core/plugins/global_configuration.rb' require 'aws-sdk-core/plugins/regional_endpoint.rb' require 'aws-sdk-core/plugins/endpoint_discovery.rb' require 'aws-sdk-core/plugins/endpoint_pattern.rb' require 'aws-sdk-core/plugins/response_paging.rb' require 'aws-sdk-core/plugins/stub_responses.rb' require 'aws-sdk-core/plugins/idempotency_token.rb' require 'aws-sdk-core/plugins/jsonvalue_converter.rb' require 'aws-sdk-core/plugins/client_metrics_plugin.rb' require 'aws-sdk-core/plugins/client_metrics_send_plugin.rb' require 'aws-sdk-core/plugins/transfer_encoding.rb' require 'aws-sdk-core/plugins/http_checksum.rb' require 'aws-sdk-core/plugins/signature_v4.rb' require 'aws-sdk-core/plugins/protocols/rest_json.rb' Aws::Plugins::GlobalConfiguration.add_identifier(:sagemakerruntime) module Aws::SageMakerRuntime # An API client for SageMakerRuntime. To construct a client, you need to configure a `:region` and `:credentials`. # # client = Aws::SageMakerRuntime::Client.new( # region: region_name, # credentials: credentials, # # ... # ) # # For details on configuring region and credentials see # the [developer guide](/sdk-for-ruby/v3/developer-guide/setup-config.html). # # See {#initialize} for a full list of supported configuration options. class Client < Seahorse::Client::Base include Aws::ClientStubs @identifier = :sagemakerruntime set_api(ClientApi::API) add_plugin(Seahorse::Client::Plugins::ContentLength) add_plugin(Aws::Plugins::CredentialsConfiguration) add_plugin(Aws::Plugins::Logging) add_plugin(Aws::Plugins::ParamConverter) add_plugin(Aws::Plugins::ParamValidator) add_plugin(Aws::Plugins::UserAgent) add_plugin(Aws::Plugins::HelpfulSocketErrors) add_plugin(Aws::Plugins::RetryErrors) add_plugin(Aws::Plugins::GlobalConfiguration) add_plugin(Aws::Plugins::RegionalEndpoint) add_plugin(Aws::Plugins::EndpointDiscovery) add_plugin(Aws::Plugins::EndpointPattern) add_plugin(Aws::Plugins::ResponsePaging) add_plugin(Aws::Plugins::StubResponses) add_plugin(Aws::Plugins::IdempotencyToken) add_plugin(Aws::Plugins::JsonvalueConverter) add_plugin(Aws::Plugins::ClientMetricsPlugin) add_plugin(Aws::Plugins::ClientMetricsSendPlugin) add_plugin(Aws::Plugins::TransferEncoding) add_plugin(Aws::Plugins::HttpChecksum) add_plugin(Aws::Plugins::SignatureV4) add_plugin(Aws::Plugins::Protocols::RestJson) # @overload initialize(options) # @param [Hash] options # @option options [required, Aws::CredentialProvider] :credentials # Your AWS credentials. This can be an instance of any one of the # following classes: # # * `Aws::Credentials` - Used for configuring static, non-refreshing # credentials. # # * `Aws::SharedCredentials` - Used for loading static credentials from a # shared file, such as `~/.aws/config`. # # * `Aws::AssumeRoleCredentials` - Used when you need to assume a role. # # * `Aws::AssumeRoleWebIdentityCredentials` - Used when you need to # assume a role after providing credentials via the web. # # * `Aws::SSOCredentials` - Used for loading credentials from AWS SSO using an # access token generated from `aws login`. # # * `Aws::ProcessCredentials` - Used for loading credentials from a # process that outputs to stdout. # # * `Aws::InstanceProfileCredentials` - Used for loading credentials # from an EC2 IMDS on an EC2 instance. # # * `Aws::ECSCredentials` - Used for loading credentials from # instances running in ECS. # # * `Aws::CognitoIdentityCredentials` - Used for loading credentials # from the Cognito Identity service. # # When `:credentials` are not configured directly, the following # locations will be searched for credentials: # # * `Aws.config[:credentials]` # * The `:access_key_id`, `:secret_access_key`, and `:session_token` options. # * ENV['AWS_ACCESS_KEY_ID'], ENV['AWS_SECRET_ACCESS_KEY'] # * `~/.aws/credentials` # * `~/.aws/config` # * EC2/ECS IMDS instance profile - When used by default, the timeouts # are very aggressive. Construct and pass an instance of # `Aws::InstanceProfileCredentails` or `Aws::ECSCredentials` to # enable retries and extended timeouts. # # @option options [required, String] :region # The AWS region to connect to. The configured `:region` is # used to determine the service `:endpoint`. When not passed, # a default `:region` is searched for in the following locations: # # * `Aws.config[:region]` # * `ENV['AWS_REGION']` # * `ENV['AMAZON_REGION']` # * `ENV['AWS_DEFAULT_REGION']` # * `~/.aws/credentials` # * `~/.aws/config` # # @option options [String] :access_key_id # # @option options [Boolean] :active_endpoint_cache (false) # When set to `true`, a thread polling for endpoints will be running in # the background every 60 secs (default). Defaults to `false`. # # @option options [Boolean] :adaptive_retry_wait_to_fill (true) # Used only in `adaptive` retry mode. When true, the request will sleep # until there is sufficent client side capacity to retry the request. # When false, the request will raise a `RetryCapacityNotAvailableError` and will # not retry instead of sleeping. # # @option options [Boolean] :client_side_monitoring (false) # When `true`, client-side metrics will be collected for all API requests from # this client. # # @option options [String] :client_side_monitoring_client_id ("") # Allows you to provide an identifier for this client which will be attached to # all generated client side metrics. Defaults to an empty string. # # @option options [String] :client_side_monitoring_host ("127.0.0.1") # Allows you to specify the DNS hostname or IPv4 or IPv6 address that the client # side monitoring agent is running on, where client metrics will be published via UDP. # # @option options [Integer] :client_side_monitoring_port (31000) # Required for publishing client metrics. The port that the client side monitoring # agent is running on, where client metrics will be published via UDP. # # @option options [Aws::ClientSideMonitoring::Publisher] :client_side_monitoring_publisher (Aws::ClientSideMonitoring::Publisher) # Allows you to provide a custom client-side monitoring publisher class. By default, # will use the Client Side Monitoring Agent Publisher. # # @option options [Boolean] :convert_params (true) # When `true`, an attempt is made to coerce request parameters into # the required types. # # @option options [Boolean] :correct_clock_skew (true) # Used only in `standard` and adaptive retry modes. Specifies whether to apply # a clock skew correction and retry requests with skewed client clocks. # # @option options [Boolean] :disable_host_prefix_injection (false) # Set to true to disable SDK automatically adding host prefix # to default service endpoint when available. # # @option options [String] :endpoint # The client endpoint is normally constructed from the `:region` # option. You should only configure an `:endpoint` when connecting # to test or custom endpoints. This should be a valid HTTP(S) URI. # # @option options [Integer] :endpoint_cache_max_entries (1000) # Used for the maximum size limit of the LRU cache storing endpoints data # for endpoint discovery enabled operations. Defaults to 1000. # # @option options [Integer] :endpoint_cache_max_threads (10) # Used for the maximum threads in use for polling endpoints to be cached, defaults to 10. # # @option options [Integer] :endpoint_cache_poll_interval (60) # When :endpoint_discovery and :active_endpoint_cache is enabled, # Use this option to config the time interval in seconds for making # requests fetching endpoints information. Defaults to 60 sec. # # @option options [Boolean] :endpoint_discovery (false) # When set to `true`, endpoint discovery will be enabled for operations when available. # # @option options [Aws::Log::Formatter] :log_formatter (Aws::Log::Formatter.default) # The log formatter. # # @option options [Symbol] :log_level (:info) # The log level to send messages to the `:logger` at. # # @option options [Logger] :logger # The Logger instance to send log messages to. If this option # is not set, logging will be disabled. # # @option options [Integer] :max_attempts (3) # An integer representing the maximum number attempts that will be made for # a single request, including the initial attempt. For example, # setting this value to 5 will result in a request being retried up to # 4 times. Used in `standard` and `adaptive` retry modes. # # @option options [String] :profile ("default") # Used when loading credentials from the shared credentials file # at HOME/.aws/credentials. When not specified, 'default' is used. # # @option options [Proc] :retry_backoff # A proc or lambda used for backoff. Defaults to 2**retries * retry_base_delay. # This option is only used in the `legacy` retry mode. # # @option options [Float] :retry_base_delay (0.3) # The base delay in seconds used by the default backoff function. This option # is only used in the `legacy` retry mode. # # @option options [Symbol] :retry_jitter (:none) # A delay randomiser function used by the default backoff function. # Some predefined functions can be referenced by name - :none, :equal, :full, # otherwise a Proc that takes and returns a number. This option is only used # in the `legacy` retry mode. # # @see https://www.awsarchitectureblog.com/2015/03/backoff.html # # @option options [Integer] :retry_limit (3) # The maximum number of times to retry failed requests. Only # ~ 500 level server errors and certain ~ 400 level client errors # are retried. Generally, these are throttling errors, data # checksum errors, networking errors, timeout errors, auth errors, # endpoint discovery, and errors from expired credentials. # This option is only used in the `legacy` retry mode. # # @option options [Integer] :retry_max_delay (0) # The maximum number of seconds to delay between retries (0 for no limit) # used by the default backoff function. This option is only used in the # `legacy` retry mode. # # @option options [String] :retry_mode ("legacy") # Specifies which retry algorithm to use. Values are: # # * `legacy` - The pre-existing retry behavior. This is default value if # no retry mode is provided. # # * `standard` - A standardized set of retry rules across the AWS SDKs. # This includes support for retry quotas, which limit the number of # unsuccessful retries a client can make. # # * `adaptive` - An experimental retry mode that includes all the # functionality of `standard` mode along with automatic client side # throttling. This is a provisional mode that may change behavior # in the future. # # # @option options [String] :secret_access_key # # @option options [String] :session_token # # @option options [Boolean] :stub_responses (false) # Causes the client to return stubbed responses. By default # fake responses are generated and returned. You can specify # the response data to return or errors to raise by calling # {ClientStubs#stub_responses}. See {ClientStubs} for more information. # # ** Please note ** When response stubbing is enabled, no HTTP # requests are made, and retries are disabled. # # @option options [Boolean] :validate_params (true) # When `true`, request parameters are validated before # sending the request. # # @option options [URI::HTTP,String] :http_proxy A proxy to send # requests through. Formatted like 'http://proxy.com:123'. # # @option options [Float] :http_open_timeout (15) The number of # seconds to wait when opening a HTTP session before raising a # `Timeout::Error`. # # @option options [Integer] :http_read_timeout (60) The default # number of seconds to wait for response data. This value can # safely be set per-request on the session. # # @option options [Float] :http_idle_timeout (5) The number of # seconds a connection is allowed to sit idle before it is # considered stale. Stale connections are closed and removed # from the pool before making a request. # # @option options [Float] :http_continue_timeout (1) The number of # seconds to wait for a 100-continue response before sending the # request body. This option has no effect unless the request has # "Expect" header set to "100-continue". Defaults to `nil` which # disables this behaviour. This value can safely be set per # request on the session. # # @option options [Boolean] :http_wire_trace (false) When `true`, # HTTP debug output will be sent to the `:logger`. # # @option options [Boolean] :ssl_verify_peer (true) When `true`, # SSL peer certificates are verified when establishing a # connection. # # @option options [String] :ssl_ca_bundle Full path to the SSL # certificate authority bundle file that should be used when # verifying peer certificates. If you do not pass # `:ssl_ca_bundle` or `:ssl_ca_directory` the the system default # will be used if available. # # @option options [String] :ssl_ca_directory Full path of the # directory that contains the unbundled SSL certificate # authority files for verifying peer certificates. If you do # not pass `:ssl_ca_bundle` or `:ssl_ca_directory` the the # system default will be used if available. # def initialize(*args) super end # @!group API Operations # After you deploy a model into production using Amazon SageMaker # hosting services, your client applications use this API to get # inferences from the model hosted at the specified endpoint. # # For an overview of Amazon SageMaker, see [How It Works][1]. # # Amazon SageMaker strips all POST headers except those supported by the # API. Amazon SageMaker might add additional headers. You should not # rely on the behavior of headers outside those enumerated in the # request syntax. # # Calls to `InvokeEndpoint` are authenticated by using AWS Signature # Version 4. For information, see [Authenticating Requests (AWS # Signature Version 4)][2] in the *Amazon S3 API Reference*. # # A customer's model containers must respond to requests within 60 # seconds. The model itself can have a maximum processing time of 60 # seconds before responding to the /invocations. If your model is going # to take 50-60 seconds of processing time, the SDK socket timeout # should be set to be 70 seconds. # # Endpoints are scoped to an individual account, and are not public. The # URL does not contain the account ID, but Amazon SageMaker determines # the account ID from the authentication token that is supplied by the # caller. # # # # # # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/how-it-works.html # [2]: http://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html # # @option params [required, String] :endpoint_name # The name of the endpoint that you specified when you created the # endpoint using the [CreateEndpoint][1] API. # # # # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html # # @option params [required, String, StringIO, File] :body # Provides input data, in the format specified in the `ContentType` # request header. Amazon SageMaker passes all of the data in the body to # the model. # # For information about the format of the request body, see [Common Data # Formats-Inference][1]. # # # # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html # # @option params [String] :content_type # The MIME type of the input data in the request body. # # @option params [String] :accept # The desired MIME type of the inference in the response. # # @option params [String] :custom_attributes # Provides additional information about a request for an inference # submitted to a model hosted at an Amazon SageMaker endpoint. The # information is an opaque value that is forwarded verbatim. You could # use this value, for example, to provide an ID that you can use to # track a request or to provide other metadata that a service endpoint # was programmed to process. The value must consist of no more than 1024 # visible US-ASCII characters as specified in [Section 3.3.6. Field # Value Components][1] of the Hypertext Transfer Protocol (HTTP/1.1). # This feature is currently supported in the AWS SDKs but not in the # Amazon SageMaker Python SDK. # # # # [1]: https://tools.ietf.org/html/rfc7230#section-3.2.6 # # @option params [String] :target_model # The model to request for inference when invoking a multi-model # endpoint. # # @option params [String] :target_variant # Specify the production variant to send the inference request to when # invoking an endpoint that is running two or more variants. Note that # this parameter overrides the default behavior for the endpoint, which # is to distribute the invocation traffic based on the variant weights. # # @return [Types::InvokeEndpointOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods: # # * {Types::InvokeEndpointOutput#body #body} => String # * {Types::InvokeEndpointOutput#content_type #content_type} => String # * {Types::InvokeEndpointOutput#invoked_production_variant #invoked_production_variant} => String # * {Types::InvokeEndpointOutput#custom_attributes #custom_attributes} => String # # @example Request syntax with placeholder values # # resp = client.invoke_endpoint({ # endpoint_name: "EndpointName", # required # body: "data", # required # content_type: "Header", # accept: "Header", # custom_attributes: "CustomAttributesHeader", # target_model: "TargetModelHeader", # target_variant: "TargetVariantHeader", # }) # # @example Response structure # # resp.body #=> String # resp.content_type #=> String # resp.invoked_production_variant #=> String # resp.custom_attributes #=> String # # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InvokeEndpoint AWS API Documentation # # @overload invoke_endpoint(params = {}) # @param [Hash] params ({}) def invoke_endpoint(params = {}, options = {}) req = build_request(:invoke_endpoint, params) req.send_request(options) end # @!endgroup # @param params ({}) # @api private def build_request(operation_name, params = {}) handlers = @handlers.for(operation_name) context = Seahorse::Client::RequestContext.new( operation_name: operation_name, operation: config.api.operation(operation_name), client: self, params: params, config: config) context[:gem_name] = 'aws-sdk-sagemakerruntime' context[:gem_version] = '1.27.0' Seahorse::Client::Request.new(handlers, context) end # @api private # @deprecated def waiter_names [] end class << self # @api private attr_reader :identifier # @api private def errors_module Errors end end end end